0

I am trying to cluster this network. The vertices are tags and the edges depict the co-occurance of these tags. The edge widths show the number of times a tag pair occurs. 'energy' and 'electricity' occur the most together.

I tried using community detection algorithms in R, especially edge.between.community which gives a modularity of 0.35 with this network. fastgreedy.community does not work on a weighted-edge graph. Is there any other algorithm somebody could suggest for this specific case? I am a novice in both graph theory and R.

Community
  • 1
  • 1
Divi
  • 1,614
  • 13
  • 23
  • Can you provide some sample data? – Gary Weissman Apr 24 '14 at 01:38
  • g <- graph( c(1,2, 1,2, 1,2, 1,2, 1,2, 1,2, 1,2, 1,2, 1,3, 2,3, 3,5), n=5, directed=FALSE ) E(g)$width <- count.multiple(g) plot(g, layout=layout.circle, edge.curved=FALSE, vertex.label=c("a","b","c","d","e")) – Divi Apr 24 '14 at 02:31
  • Whichever you like best. – Gabor Csardi Apr 24 '14 at 04:11
  • 1
    possible duplicate of [What are the differences between community detection algorithms in igraph?](http://stackoverflow.com/questions/9471906/what-are-the-differences-between-community-detection-algorithms-in-igraph) – Tamás Apr 24 '14 at 15:44

0 Answers0